scholarly journals Benchmarking Coordination Number Prediction Algorithms on Inorganic Crystal Structures

2021 ◽  
Author(s):  
Hillary Pan ◽  
Alex Ganose ◽  
Matthew Horton ◽  
Muratahan Aykol ◽  
Kristin Persson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Crystal Structures ◽  
Near Neighbor ◽  
Research Literature ◽  
Small Perturbations ◽  
Materials Properties ◽  
Coordination Numbers ◽  
Prediction Algorithms ◽  
Inorganic Crystal ◽  
Benchmark Suite

Coordination numbers and geometries form a theoretical framework for understanding and predicting materials properties. Algorithms to determine coordination numbers automatically are increasingly used for machine learning and automatic structural analysis. In this work, we introduce MaterialsCoord, a benchmark suite containing 56 experimentally-derived crystal structures (spanning elements, binaries, and ternary compounds) and their corresponding coordination environments as described in the research literature. We also describe CrystalNN, a novel algorithm for determining near neighbors. We compare CrystalNN against 7 existing near-neighbor algorithms on the MaterialsCoord benchmark, finding CrystalNN to perform similarly to several well-established algorithms. For each algorithm, we also assess computational demand and sensitivity towards small perturbations that mimic thermal motion. Finally, we investigate the similarity between bonding algorithms when applied to the Materials Project database. We expect that this work will aid the development of coordination prediction algorithms as well as improve structural descriptors for machine learning and other applications.

scholarly journals Benchmarking Coordination Number Prediction Algorithms on Inorganic Crystal Structures

2021 ◽  
Author(s):  
Hillary Pan ◽  
Alex Ganose ◽  
Matthew Horton ◽  
Muratahan Aykol ◽  
Kristin Persson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Crystal Structures ◽  
Near Neighbor ◽  
Research Literature ◽  
Small Perturbations ◽  
Materials Properties ◽  
Coordination Numbers ◽  
Prediction Algorithms ◽  
Inorganic Crystal ◽  
Benchmark Suite

Coordination numbers and geometries form a theoretical framework for understanding and predicting materials properties. Algorithms to determine coordination numbers automatically are increasingly used for machine learning and automatic structural analysis. In this work, we introduce MaterialsCoord, a benchmark suite containing 56 experimentally-derived crystal structures (spanning elements, binaries, and ternary compounds) and their corresponding coordination environments as described in the research literature. We also describe CrystalNN, a novel algorithm for determining near neighbors. We compare CrystalNN against 7 existing near-neighbor algorithms on the MaterialsCoord benchmark, finding CrystalNN to perform similarly to several well-established algorithms. For each algorithm, we also assess computational demand and sensitivity towards small perturbations that mimic thermal motion. Finally, we investigate the similarity between bonding algorithms when applied to the Materials Project database. We expect that this work will aid the development of coordination prediction algorithms as well as improve structural descriptors for machine learning and other applications.

scholarly journals Benchmarking Coordination Number Prediction Algorithms on Inorganic Crystal Structures

2020 ◽  
Author(s):  
Hillary Pan ◽  
Alex Ganose ◽  
Matthew Horton ◽  
Muratahan Aykol ◽  
Kristin Persson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Crystal Structures ◽  
Near Neighbor ◽  
Research Literature ◽  
Small Perturbations ◽  
Materials Properties ◽  
Coordination Numbers ◽  
Prediction Algorithms ◽  
Inorganic Crystal ◽  
Benchmark Suite

Coordination numbers and geometries form a theoretical framework for understanding and predicting materials properties. Algorithms to determine coordination numbers automatically are increasingly used for machine learning and automatic structural analysis. In this work, we introduce MaterialsCoord, a benchmark suite containing 56 experimentally-derived crystal structures (spanning elements, binaries, and ternary compounds) and their corresponding coordination environments as described in the research literature. We also describe CrystalNN, a novel algorithm for determining near neighbors. We compare CrystalNN against 7 existing near-neighbor algorithms on the MaterialsCoord benchmark, finding CrystalNN to be the most accurate overall. For each algorithm, we also assess computational demand and sensitivity towards small perturbations that mimic thermal motion. Finally, we investigate the similarity between bonding algorithms when applied to the Materials Project database. We expect that this work will aid the development of coordination prediction algorithms and improve the accuracy of structural descriptors for machine learning and other applications.

scholarly journals Correction to Benchmarking Coordination Number Prediction Algorithms on Inorganic Crystal Structures

2021 ◽  
Author(s):  
Hillary Pan ◽  
Alex M. Ganose ◽  
Matthew Horton ◽  
Muratahan Aykol ◽  
Kristin Persson ◽  
...  
Keyword(s):  
Crystal Structures ◽  
Coordination Number ◽  
Prediction Algorithms ◽  
Inorganic Crystal

scholarly journals Benchmarking Coordination Number Prediction Algorithms on Inorganic Crystal Structures

2021 ◽  
Vol 60 (3) ◽  
pp. 1590-1603
Author(s):  
Hillary Pan ◽  
Alex M. Ganose ◽  
Matthew Horton ◽  
Muratahan Aykol ◽  
Kristin A. Persson ◽  
...  
Keyword(s):  
Crystal Structures ◽  
Coordination Number ◽  
Prediction Algorithms ◽  
Inorganic Crystal

scholarly journals Data-driven learning and prediction of inorganic crystal structures

2018 ◽  
Vol 211 ◽  
pp. 45-59 ◽  
Author(s):  
Volker L. Deringer ◽  
Davide M. Proserpio ◽  
Gábor Csányi ◽  
Chris J. Pickard
Keyword(s):  
Crystal Structure ◽  
Machine Learning ◽  
Crystal Structures ◽  
Structure Prediction ◽  
Data Driven ◽  
Interatomic Potentials ◽  
Crystal Structure Prediction ◽  
Energy Landscapes ◽  
Inorganic Crystal

Machine learning-based interatomic potentials, fitting energy landscapes “on the fly”, are emerging and promising tools for crystal structure prediction.

scholarly journals Topological representations of crystalline compounds for the machine-learning prediction of materials properties

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Yi Jiang ◽  
Dong Chen ◽  
Xin Chen ◽  
Tangyi Li ◽  
Guo-Wei Wei ◽  
...  
Keyword(s):  
Machine Learning ◽  
Crystal Structures ◽  
Algebraic Topology ◽  
Density Functional ◽  
Persistent Homology ◽  
Absolute Error ◽  
Materials Properties ◽  
Coulomb Matrix ◽  
Low Dimensional ◽  
Many Body Interactions

AbstractAccurate theoretical predictions of desired properties of materials play an important role in materials research and development. Machine learning (ML) can accelerate the materials design by building a model from input data. For complex datasets, such as those of crystalline compounds, a vital issue is how to construct low-dimensional representations for input crystal structures with chemical insights. In this work, we introduce an algebraic topology-based method, called atom-specific persistent homology (ASPH), as a unique representation of crystal structures. The ASPH can capture both pairwise and many-body interactions and reveal the topology-property relationship of a group of atoms at various scales. Combined with composition-based attributes, ASPH-based ML model provides a highly accurate prediction of the formation energy calculated by density functional theory (DFT). After training with more than 30,000 different structure types and compositions, our model achieves a mean absolute error of 61 meV/atom in cross-validation, which outperforms previous work such as Voronoi tessellations and Coulomb matrix method using the same ML algorithm and datasets. Our results indicate that the proposed topology-based method provides a powerful computational tool for predicting materials properties compared to previous works.

iMLBench: A Machine Learning Benchmark Suite for CPU-GPU Integrated Architectures

2020 ◽  
pp. 1-1
Author(s):  
Chenyang Zhang ◽  
Feng Zhang ◽  
Xiaoguang Guo ◽  
Bingsheng He ◽  
Xiao Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Benchmark Suite

The Gold Sulfates MAu(S04)2 (M = Na, K, Rb)

2001 ◽  
Vol 56 (12) ◽  
pp. 1340-1343 ◽  
Author(s):  
Mathias S. Wickleder ◽  
Oliver Büchner
Keyword(s):  
Sulfuric Acid ◽  
Single Crystals ◽  
Crystal Structures ◽  
Structural Features ◽  
Monovalent Cations ◽  
Coordination Numbers ◽  
Square Planar ◽  
Oxygen Atoms

AbstractThe evaporation of a solution of Au(OH)3 and Na2So4 in conc. sulfuric acid led to yellow single crystals of NaAu(SO4)2 (monoclinic, P21/n, Z = 2, a = 469.1, b = 845.9, c = 831.2 pm, β = 95.7°). Analogous procedures with K2SO4 or Rb2SO4 instead of Na2SO4 yielded single crystals of KAu(SO4)2 (monoclinic, C2/c, Z = 4, a = 1109.8, b = 724.2, c = 941.1 pm, β = 118.4°) and RbAu(S04)2, respectively, (triclinic, P1̄, Z = 1, a = 423.6, b = 497.5, c = 889.0 pm, a = 76.4°, β = 88.4°, γ = 73.5°). Although the crystal structures of the three sulfates are not isotypic they show similar structural features: The gold atoms are coordinated by four oxygen atoms in a square planar manner. These oxygen atoms belong to four SO42- ions which link the [AUO4] units to infinite chains according to 1∞[Au(SO4)4/ 2]- . These chains are connected via the monovalent cations which show coordination numbers of 6 (Na+), 10 (K+) and 12 (Rb+), respectively.

Dimorphic ThNi2P2 with BaCu2S2 and CaBe2Ge2 Type Structure

1994 ◽  
Vol 49 (8) ◽  
pp. 1074-1080 ◽  
Author(s):  
Jörg H. Albering ◽  
Wolfgang Jeitschko
Keyword(s):  
Phase Transformation ◽  
High Temperature ◽  
Crystal Structures ◽  
Type Structure ◽  
Variable Parameters ◽  
Higher Symmetry ◽  
X Ray ◽  
Coordination Numbers ◽  
Structure Factors ◽  
High Temperature Form

Two modifications of ThNi2P2 were prepared in a tin flux at 850 °C (α-ThNi2P2) and 1000 °C (β-ThNi2P2). The crystal structures of both modifications were refined from single­crystal X-ray data. α-ThNi2P2 (BaCu2S2 type structure): Pnma. a = 819.69(5), b = 394.28(3), c = 981.54(7) pm. R = 0.028 for 32 variables and 654 structure factors: β-ThNi2P2 (CaBe2Ge2 type structure): P4/nmm, a = 408.5(1), c = 908.0(3) pm, R = 0.033 for 15 variable parameters and 261 F values. Although the two structures are closely related, they can be transformed into each other only by a reconstructive phase transformation. The differences and similari­ties of the two structures are discussed. The high temperature form has higher symmetry, a smaller number of variable positional parameters, and a tendency for higher coordination numbers.

Sign in / Sign up

Export Citation Format

Share Document